Issue No. 04 - July/August (2007 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2007.66
Siriwan Suebnukarn , Thammasat University Dental School
Peter Haddawy , Asian Institute of Technology
The Collaborative Medical Tutor (COMET) is an intelligent tutoring system for medical problem-based learning (PBL). COMET emulates live human-tutored medical PBL sessions as much as possible while also letting students participate collaboratively from disparate locations. COMET uses Bayesian networks to model both individual and group student knowledge and activity. Generic domain-independent tutoring algorithms use these student and group models to generate tutoring hints. COMET incorporates a multimodal interface that integrates text and graphics in a rich communication channel between the students and the system and among students in the group. A comparison of learning outcomes shows that students using the COMET system achieved significantly higher clinical-reasoning gains than students in human-tutored sessions. This article is part of a special issue on intelligent educational systems.
intelligent tutoring systems, computer-supported collaborative learning, Bayesian networks, medicine, problem-based learning, empirical evaluation
P. Haddawy and S. Suebnukarn, "COMET: A Collaborative Tutoring System for Medical Problem-Based Learning," in IEEE Intelligent Systems, vol. 22, no. , pp. 70-77, 2007.